Robust Partial Least Squares Path Modeling

Tamara Svenja Schamberger, Florian Schuberth, Jörg Henseler, Theo K. Dijkstra

Research output: Contribution to journalArticleAcademicpeer-review

10 Downloads (Pure)

Abstract

Outliers can seriously distort the results of statistical analyses and thus threaten the validity of structural equation models. As a remedy, this article introduces a robust variant of Partial Least Squares Path Modeling (PLS) and consistent Partial Least Squares (PLSc) called robust PLS and robust PLSc, respectively, which are robust against distortion caused by outliers. Consequently, robust PLS/PLSc allows to estimate structural models containing constructs modeled as composites and common factors even if empirical data are contaminated by outliers. A Monte Carlo simulation with various population models, sample sizes, and extents of outliers shows that robust PLS/PLSc can deal with outlier shares of up to 50% without distorting the estimates. The simulation also shows that robust PLS/PLSc should always be preferred over its traditional counterparts if the data contain outliers. To demonstrate the relevance for empirical research, robust PLSc is applied to two empirical examples drawn from the extant literature.
Original languageEnglish
Number of pages28
JournalBehaviormetrika
Early online date19 Jul 2019
DOIs
Publication statusE-pub ahead of print/First online - 19 Jul 2019

Fingerprint

outlier
modeling
simulation

Keywords

  • UT-Hybrid-D
  • Robust partial least squares path modeling
  • Robust correlation
  • Robust consistent partial least squares
  • Composites
  • Outliers

Cite this

@article{58a2eed59f104bbb9d46efded3961397,
title = "Robust Partial Least Squares Path Modeling",
abstract = "Outliers can seriously distort the results of statistical analyses and thus threaten the validity of structural equation models. As a remedy, this article introduces a robust variant of Partial Least Squares Path Modeling (PLS) and consistent Partial Least Squares (PLSc) called robust PLS and robust PLSc, respectively, which are robust against distortion caused by outliers. Consequently, robust PLS/PLSc allows to estimate structural models containing constructs modeled as composites and common factors even if empirical data are contaminated by outliers. A Monte Carlo simulation with various population models, sample sizes, and extents of outliers shows that robust PLS/PLSc can deal with outlier shares of up to 50{\%} without distorting the estimates. The simulation also shows that robust PLS/PLSc should always be preferred over its traditional counterparts if the data contain outliers. To demonstrate the relevance for empirical research, robust PLSc is applied to two empirical examples drawn from the extant literature.",
keywords = "UT-Hybrid-D, Robust partial least squares path modeling, Robust correlation, Robust consistent partial least squares, Composites, Outliers",
author = "Schamberger, {Tamara Svenja} and Florian Schuberth and J{\"o}rg Henseler and Dijkstra, {Theo K.}",
note = "Springer deal",
year = "2019",
month = "7",
day = "19",
doi = "10.1007/s41237-019-00088-2",
language = "English",
journal = "Behaviormetrika",
issn = "0385-7417",
publisher = "Behaviormetric Society of Japan",

}

Robust Partial Least Squares Path Modeling. / Schamberger, Tamara Svenja; Schuberth, Florian ; Henseler, Jörg ; Dijkstra, Theo K.

In: Behaviormetrika, 19.07.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Robust Partial Least Squares Path Modeling

AU - Schamberger, Tamara Svenja

AU - Schuberth, Florian

AU - Henseler, Jörg

AU - Dijkstra, Theo K.

N1 - Springer deal

PY - 2019/7/19

Y1 - 2019/7/19

N2 - Outliers can seriously distort the results of statistical analyses and thus threaten the validity of structural equation models. As a remedy, this article introduces a robust variant of Partial Least Squares Path Modeling (PLS) and consistent Partial Least Squares (PLSc) called robust PLS and robust PLSc, respectively, which are robust against distortion caused by outliers. Consequently, robust PLS/PLSc allows to estimate structural models containing constructs modeled as composites and common factors even if empirical data are contaminated by outliers. A Monte Carlo simulation with various population models, sample sizes, and extents of outliers shows that robust PLS/PLSc can deal with outlier shares of up to 50% without distorting the estimates. The simulation also shows that robust PLS/PLSc should always be preferred over its traditional counterparts if the data contain outliers. To demonstrate the relevance for empirical research, robust PLSc is applied to two empirical examples drawn from the extant literature.

AB - Outliers can seriously distort the results of statistical analyses and thus threaten the validity of structural equation models. As a remedy, this article introduces a robust variant of Partial Least Squares Path Modeling (PLS) and consistent Partial Least Squares (PLSc) called robust PLS and robust PLSc, respectively, which are robust against distortion caused by outliers. Consequently, robust PLS/PLSc allows to estimate structural models containing constructs modeled as composites and common factors even if empirical data are contaminated by outliers. A Monte Carlo simulation with various population models, sample sizes, and extents of outliers shows that robust PLS/PLSc can deal with outlier shares of up to 50% without distorting the estimates. The simulation also shows that robust PLS/PLSc should always be preferred over its traditional counterparts if the data contain outliers. To demonstrate the relevance for empirical research, robust PLSc is applied to two empirical examples drawn from the extant literature.

KW - UT-Hybrid-D

KW - Robust partial least squares path modeling

KW - Robust correlation

KW - Robust consistent partial least squares

KW - Composites

KW - Outliers

U2 - 10.1007/s41237-019-00088-2

DO - 10.1007/s41237-019-00088-2

M3 - Article

JO - Behaviormetrika

JF - Behaviormetrika

SN - 0385-7417

ER -